⚡ Hit your SLA, cut costs. Download the Friendli Guide to Inference Performance Optimization ➜
Product
Solutions
Developers
Company
Featured models
All models
21,944 results found
Trending
Model Name
Input
Output
Type
alphaedge-ai
Qwen3.5-2B-isl-32768
Base
Deploy
Qwen3.5-2B-mar-32768
Qwen3.5-0.8B-kat-32768
Qwen3.5-0.8B-dan-16384
Qwen3.5-0.8B-gle-16384
yiiiiiz
qwen3vl-8b-assembly-sft-20260528h-stage4
Adapter
Qwen3.5-2B-mar-16384
MLXBits
huihui-qwen3-vl-30b-abliterated-4bit
Quantized
Qwen3.5-4B-tur-16384
Qwen3.5-2B-tur-16384
Qwen3.5-2B-ltz-16384
Qwen3.5-0.8B-tur-32768
Qwen3.5-0.8B-scn-16384
Qwen3.5-0.8B-aze-16384
qwen3vl-8b-assembly-sft-20260528g-stage3
Qwen3.5-2B-nep-32768
Qwen3.5-0.8B-ukr-16384
Qwen3.5-4B-nep-32768
Qwen3.5-0.8B-vie-32768
Qwen3.5-0.8B-jpn-16384
RoelV
Qwopus3.6-27B-v2-oQ6-fp16-mtp
Qwen3.5-0.8B-sin-16384
Qwen3.5-2B-slv-32768
krzonkalla
test-974
Qwen3.5-0.8B-ron-32768
Qwen3.5-4B-isl-16384
qwen3vl-8b-assembly-sft-20260528f-stage2
Qwen3.5-4B-lvs-16384
ethantsliu
sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed3
Qwen3.5-4B-slv-32768
Qwen3.5-0.8B-ceb-16384
sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed2
Qwen3.5-0.8B-kor-16384
sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed1
glyphsoftware
gemma-4-26b-a4b-opus-4.7-distilled
Fine-tuned
Qwen3.5-2B-zho-32768
Qwen3.5-2B-lao-16384
Qwen3.5-0.8B-srp-16384
sft_gsm8k_qwen3.6-27b_as_llama-3.1-8b_seed2
sft_gsm8k_qwen3.6-27b_as_llama-3.1-8b_seed1
Qwen3.5-0.8B-kan-32768
datas3nt
qwen2vl-polygen-lora-r16-1000